lfnovo/esperanto
A unified interface for various AI model providers
Uses direct HTTP communication with `httpx` rather than vendor SDKs, eliminating dependencies and overhead while maintaining provider-specific optimizations. Supports 17+ providers across LLMs, embeddings, reranking, speech-to-text, and text-to-speech with standardized response objects—enabling seamless provider switching without code changes. Offers both sync and async APIs with streaming, structured output, and optional LangChain integration for production deployments.
157 stars and 22,190 monthly downloads. Available on PyPI.
Stars
157
Forks
24
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Monthly downloads
22,190
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/lfnovo/esperanto"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
apocas/restai
RESTai is an AIaaS (AI as a Service) open-source platform. Built on top of LlamaIndex &...
sbhjt-gr/InferrLM
On-device AI for iOS & Android
baidubce/bce-qianfan-sdk
Provide best practices for LMOps, as well as elegant and convenient access to the features of...
ProviderProtocol/ai
0-DEP AI DX SDK
Muvon/octolib
The lib to power AI tools.